OpenAI
o1-mini benchmark results
7 results on 4 benchmarks from 2 sources.
Closed Released: Sep 12, 2024 Updated Oct 23, 2026
Also listed as: o1-mini-2024-09-12_high · o1-mini (high) · o1-mini-2024-09-12_medium · o1-mini (medium)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1337 | 239 | Overall, style control on; 51981 votes; 95% CI 1333–1340 | Official leaderboard | Oct 22, 2026 |
| GPQA Diamond | 62.4% | 181 | Epoch AI run, accuracy; effort: high | Independent run | Feb 13, 2025 |
| GPQA Diamond | 59.5% | 184 | Epoch AI run, accuracy; effort: medium | Independent run | Jan 27, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 46.9% | 171 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: high | Independent run | Mar 6, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 44.7% | 177 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium | Independent run | Mar 6, 2025 |
| MATH Level 5 | 89.2% | 24 | Epoch AI run, accuracy; effort: high | Independent run | Feb 13, 2025 |
| MATH Level 5 | 84.3% | 31 | Epoch AI run, accuracy; effort: medium | Independent run | Jan 27, 2025 |
Where o1-mini ranks
Primary setting, one best-sourced score per model (official / independent first); neighbours in brackets.
| Benchmark | Score | Rank | Nearby models | #1 |
|---|---|---|---|---|
| MATH Level 5 | 89.2% | #18 / 94 | Grok-3 mini 90.9% · DeepSeek-R1-Distill-Llama-70B 89.9% · Grok 3 88.8% · GPT-4.1 mini 87.3% | GPT-598.1% |
| LMArena Text | 1337 | #218 / 392 | Granite 4.2 30B 1340 · GPT-5 nano 1338 · Gemini Advanced (0514) 1336 · Grok-2 1336 | Gemini 4 Argon1517 |
| GPQA Diamond | 62.4% | #121 / 217 | DeepSeek-R1-Distill-Qwen-32B 64.1% · Gemini 2.0 Flash (Feb 2025) 64.1% · gpt-oss-20b 60.8% · Mistral Medium 3 59.5% | Gemini 4 Argon96.4% |
| AIME (OTIS Mock AIME 2024–2025) | 46.9% | #119 / 200 | gpt-oss-20b 50.8% · DeepSeek-R1-Distill-Qwen-14B 50.6% · GPT-4.1 mini 44.7% · deepseek-r1-0528-qwen3-8b 43.9% | Gemini 4 Argon100.0% |
Other OpenAI models
GPT-5GPT-5.2o3GPT-4.1GPT-5.4o4-miniGPT-4 Turbo (Nov 2023)GPT-4o (May 2024)GPT-5 miniGPT-5.1GPT-4.1 miniGPT-4o mini
FAQ
Where does o1-mini rank best?
MATH Level 5: #18 of 94 (89.2%); #1 there is GPT-5 (98.1%).
Where do these o1-mini scores come from?
From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.